ragdoll-studio

Amazing work! This technology is only going to improve. Soon there will be an infinite library of rich and dynamic games, films, podcasts, etc. - a totally unique and fascinating experience tailored to you that's only a prompt away. I've been working on something adjacent to this concept with Ragdoll (https://github.com/bennyschmidt/ragdoll-studio), but focused not just on creating characters but producing creative deliverables using them.

The goal of Ragdoll is to be the absolute best free/open source AI creative tool for making: - Stories - Copywriting - Icons - Logos - Animations - Photos - Illustrations - Concept art - TV shows - Podcasts - Cinematics - Cutscenes - Films - Music - Sound effects - Speech - Game NPCS & characters - & more! There's also a Community Site where creators can share their AI creations (stories, games, movies, etc.) and also the Ragdolls they used to create them: https://ragdoll-studio.vercel.app/ Think of a "Ragdoll" like an "AI Character" (in a character.ai sense) that uses RAG to let the user "load knowledge" and extend the character to go way beyond storytelling: For example, they can create art and music in a certain style. See examples: https://github.com/bennyschmidt/ragdoll-studio/tree/master/e... Ragdoll is also easily forkable :) The u

- Basic internet search (I start ollama CLI faster than I can start a browser - https://ollama.com) - Formatting/changing text - Troubleshooting code, esp. new frameworks/libs - Recipes - Data entry - Organizing thoughts: High-level lists, comparison, classification, synonyms, jargon & nomenclature - Learning esp. by analogy and example RAG for: - Website assistants (https://github.com/bennyschmidt/ragdoll-studio/tree/master/e...) - Game NPCs (https://github.com/bennyschmidt/ragdoll-studio/tree/master/e...) - Discord/Slack/forum bots (https://github.com/bennyschmidt/ragdoll-studio/tree/master/e...) - Character-driven storytelling and video game concept art (https://github.com/bennyschmidt/ragdoll-studio/tree/master/r...)

> I always say I want AI to work offline I'm with you, I'm most excited about this too. Currently building an AI creative studio (make stories, art, music, videos, etc.) that runs locally/offline (https://github.com/bennyschmidt/ragdoll-studio). There is a lot of focus on cloud with LLMs but I can't see how the cost will make much sense for involved creative apps like video creation, etc. Present day users might not have high-end machines, but I think they all will pretty soon - this will make them buy them the way MMORPGs made everyone buy more RAM. Especially the artists and creators. Remember, Photoshop was once pretty difficult to run, you needed a great machine. I can imagine offline music/movies apps, offline search engines, back office software, etc.

This might be useful: https://github.com/bennyschmidt/ragdoll-studio

I built a JavaScript library for creating LLM-based game NPCs, here's a video demo: https://github.com/bennyschmidt/ragdoll-studio/tree/master/e... You drop all their knowledge into a file, like .txt. or .html and it uses RAG to learn everything in the file, so if it's a vendor things like shop inventory, prices, or if it's a storyteller/questgiver you can give it knowledge the player must uncover, etc. It uses the LLM for natural sounding conversations and instructions ("speak in the style of..." etc.)

> You would also need to load an enormous amount of precedential case law Very easily done. Is that it? > lack of common sense, false conclusions The AI tool doesn't replace the judge/DA/etc. it's just a very useful tool for them to use. Checkout the "RAG-based learning" section of this app I built (https://github.com/bennyschmidt/ragdoll-studio) there's a video that shows how you can effectively load new knowledge into it (I use LlamaIndex for RAG). For example, past cases that set legal precedents, and other information you want to be considered. It creates a database of the files you load in, so it's not making those assumptions like an LLM without RAG would. I think a human would be more error-prone than an LLM with vector DB of specific data + querying engine. > I don't see the utility Then you are not paying attention or haven't use

I thought Tailwind handling pseudo classes and responsive breakpoints in the className was pretty slick, but I also agree with you that they can get very long. Part of it is just organization/abstraction. Personally, when a component gets too ugly to look at it's time to abstract that away. I want all my top level components to be simple almost English looking syntax and attributes, or even no attributes, like this: import { Header, Page, Footer } from 'library'; const App = () => <> <Header /> <Page /> <Footer /> <>; Ideally I'm looking at clean components like this in my daily work, with those long classNames hidden away in a component library: https://github.com/bennyschmidt/ragdoll-studio/blob/master/r... I think even with regular CSS, styled components, etc. you're still going to have that base layer where all

It was said in jest, but you went a little overboard with: > wouldn’t even provide reliable legal tooling. There are already funded companies and even hobbyists in Discords I'm in doing this with RAG, also patient medical docs, etc. it's really great for that use case of specific document data like laws or a patient's medical history. Here are some AI assistants that I created that can interpret law, examine medical docs, help you buy shampoo, or even give you price and parts comparisons at your local auto parts store: https://github.com/bennyschmidt/ragdoll-studio/tree/master/e... I say said in jest because (and this is counter to your second point) it very likely will not replace lawyers, but become tooling for lawyers.

I've made AI assistants that are perfectly accurate with products, pricing, etc. yet still maintain a human quality: https://github.com/bennyschmidt/ragdoll-studio/tree/master/e... You can accomplish this with RAG. Your overall point is taken though, the LLM itself is not enough, fine-tuning is not always feasible, and I think no matter how good an AI persona gets at, say, teaching yoga - for some yoga students it will never replace an in-person instructor. However for a game NPC, online agent, Discord bot, etc. not to mention research, translation, tutorials, summarizing, etc. there is a lot of present day utility for LLMs.

Very cool app, if anyone wants to try the FOSS alternative to this check out Ragdoll Studio - https://github.com/bennyschmidt/ragdoll-studio Create anyone you want based on a list of documents (URLs), chat with them, have them create images in their style, tell stories, etc. (runs open models with Ollama, Stable Diffusion, etc. not OpenAI) I would be curious what Sam Altmans people make, you can share characters here: https://ragdoll-studio.vercel.app

It's a FOSS alternative because instead of using their online platform to make an account in order to interact with their characters, you instead download and run this source code without needing an account to interact with yours, and those in the community - even offline if you want. There's more to it than just chatting with AI models - these "ragdolls" are based on RAG so they are able to have distinct personalities and scoped knowledge. They can't leak info they don't know about, can't be censored from talking about things they do know about, and can be exported and shared with others on the community site. The model itself is more like the underlying engine, where the ragdoll is a specific persona that you can deploy to a variety of tasks (starting with just chat). I want to go beyond what character.ai is even dreaming of doing by ma

I added some case studies to the repo... Shopping assistants, researchers, curators, Discord/Slack bots, and game NPCs are just a few of the use cases I've built examples for so far: https://github.com/bennyschmidt/Arthas.AI/blob/master/CaseSt... I just created a separate post for this because it's a different URL and somewhat adjacent to this Show HN. But maybe it's better to keep it all in 1 article - I will leave it up to the mods :)